Imagen de Portada

Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dang, Yunkai, Jiang, Yifan, Jiang, Yizhu, Chen, Anqi, Li, Wenbin, Gao, Yang
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
por: Dang, Yunkai, et al.
Publicado: (2026)

UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
por: Dang, Yunkai, et al.
Publicado: (2026)

FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
por: Dang, Yunkai, et al.
Publicado: (2025)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
por: Qu, Liao, et al.
Publicado: (2024)

Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation
por: Zhao, Yunpu, et al.
Publicado: (2025)

UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
por: Jiao, Yang, et al.
Publicado: (2025)

Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
por: Jiang, Yibo, et al.
Publicado: (2026)

Annotation-Free Visual Reasoning for High-Resolution Large Multimodal Models via Reinforcement Learning
por: Yang, Jiacheng, et al.
Publicado: (2026)

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model
por: Zhuang, Shaobin, et al.
Publicado: (2026)

A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
por: Dang, Yunkai, et al.
Publicado: (2025)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
por: Ma, Chuofan, et al.
Publicado: (2025)

Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models
por: Zhang, Yue, et al.
Publicado: (2024)

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
por: Liu, Zeyu, et al.
Publicado: (2026)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
por: Wang, Yixu, et al.
Publicado: (2025)

Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
por: Ma, Chuofan, et al.
Publicado: (2024)

Adversarial Prompt Injection Attack on Multimodal Large Language Models
por: Ding, Meiwen, et al.
Publicado: (2026)

Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling
por: Zhou, Zikang, et al.
Publicado: (2026)

Lance: Unified Multimodal Modeling by Multi-Task Synergy
por: Fu, Fengyi, et al.
Publicado: (2026)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
por: Wang, Xinhao, et al.
Publicado: (2026)

PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models
por: Liu, Yingen, et al.
Publicado: (2024)

Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference
por: Lin, Zhihang, et al.
Publicado: (2024)

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
por: Fang, Yiyang, et al.
Publicado: (2026)

AviationLMM: A Large Multimodal Foundation Model for Civil Aviation
por: Li, Wenbin, et al.
Publicado: (2026)

Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
por: Xing, Wenbin, et al.
Publicado: (2026)

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
por: Zhang, Huichao, et al.
Publicado: (2026)

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
por: Wu, Kai, et al.
Publicado: (2024)

AToken: A Unified Tokenizer for Vision
por: Lu, Jiasen, et al.
Publicado: (2025)

LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
por: Zhao, Zihui, et al.
Publicado: (2025)

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
por: Jiang, Yutao, et al.
Publicado: (2025)

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
por: Zhou, Ziqin, et al.
Publicado: (2025)

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
por: Wen, Zimo, et al.
Publicado: (2026)

Semantic Generative Tuning for Unified Multimodal Models
por: Yu, Songsong, et al.
Publicado: (2026)

A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
por: Jiang, Siyang, et al.
Publicado: (2025)

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
por: Wu, Penghao, et al.
Publicado: (2025)

SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation
por: Chen, Zisheng, et al.
Publicado: (2025)

V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
por: Zhang, Guiwei, et al.
Publicado: (2025)

Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
por: Guan, Xiaoliu, et al.
Publicado: (2025)

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
por: Mao, Jiawei, et al.
Publicado: (2025)

Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans
por: Qin, Sizhong, et al.
Publicado: (2026)

UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space
por: Yang, Panqi, et al.
Publicado: (2025)